[PATCH v3 4/9] KVM: guest_memfd: add GUEST_MEMFD_FLAG_MIGRATABLE

guest_memfd folios are currently always marked unmovable, which
prevents the MM from invoking ->migrate_folio callback in scenarios
like compaction, offlining, etc. This is unavoidable for confidential VMs
(SEV-SNP, TDX), since memory is encrypted and copying it needs firmware
assistance. However, for non-confidential VMs (like firecracker), we
can still migrate the folios.

Add kvm_arch_supports_gmem_migration() so an architecture can control
whether migration is supported. Add GUEST_MEMFD_FLAG_MIGRATABLE so
userspace can opt-in to folio migration.

For opted-in guest_memfds, use GFP_HIGHUSER_MOVABLE so their folios can
be allocated from ZONE_MOVABLE/CMA and grouped by mobility, otherwise
keep the existing unmovable behavior.

Remove redundant WARN_ON_ONCE for checking unevictable mapping.

Signed-off-by: Shivank Garg <[email protected]>
---
 Documentation/virt/kvm/api.rst |  3 +++
 arch/x86/kvm/x86.c             |  9 +++++++++
 include/linux/kvm_host.h       |  4 ++++
 include/uapi/linux/kvm.h       |  1 +
 tools/include/uapi/linux/kvm.h |  1 +
 virt/kvm/guest_memfd.c         | 18 ++++++++++++++----
 6 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index e3003a241d5b..976921527ef9 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6461,6 +6461,9 @@ specified via KVM_CREATE_GUEST_MEMFD.  Currently defined flags:
                                without INIT_SHARED will be marked private).
                                Shared memory can be faulted into host userspace
                                page tables. Private memory cannot.
+ GUEST_MEMFD_FLAG_MIGRATABLE   Allow MM to migrate guest_memfd folios.
+                               Availability is architecture sepecific. Without
+                               this flag, folios remain unmovable.
   ============================ ================================================
 
 When the KVM MMU performs a PFN lookup to service a guest fault and the backing
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47cb9eba113b..7087b0b8f973 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -14130,6 +14130,15 @@ bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm)
 	return !kvm_arch_has_private_mem(kvm);
 }
 
+/*
+ * Migration of guest_memfd with private memory is not supported yet
+ * as this may require architecture-specific handling.
+ */
+bool kvm_arch_supports_gmem_migration(struct kvm *kvm)
+{
+	return !kvm_arch_has_private_mem(kvm);
+}
+
 #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
 int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index ab8cfaec82d3..7b2f15b21970 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -731,6 +731,7 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
 
 #ifdef CONFIG_KVM_GUEST_MEMFD
 bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm);
+bool kvm_arch_supports_gmem_migration(struct kvm *kvm);
 
 static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm)
 {
@@ -738,6 +739,9 @@ static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm)
 
 	if (!kvm || kvm_arch_supports_gmem_init_shared(kvm))
 		flags |= GUEST_MEMFD_FLAG_INIT_SHARED;
+	if (IS_ENABLED(CONFIG_MIGRATION) &&
+	    (!kvm || kvm_arch_supports_gmem_migration(kvm)))
+		flags |= GUEST_MEMFD_FLAG_MIGRATABLE;
 
 	return flags;
 }
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 419011097fa8..e1615a62ed78 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1654,6 +1654,7 @@ struct kvm_memory_attributes {
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
 #define GUEST_MEMFD_FLAG_MMAP		(1ULL << 0)
 #define GUEST_MEMFD_FLAG_INIT_SHARED	(1ULL << 1)
+#define GUEST_MEMFD_FLAG_MIGRATABLE	(1ULL << 2)
 
 struct kvm_create_guest_memfd {
 	__u64 size;
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 419011097fa8..e1615a62ed78 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1654,6 +1654,7 @@ struct kvm_memory_attributes {
 #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
 #define GUEST_MEMFD_FLAG_MMAP		(1ULL << 0)
 #define GUEST_MEMFD_FLAG_INIT_SHARED	(1ULL << 1)
+#define GUEST_MEMFD_FLAG_MIGRATABLE	(1ULL << 2)
 
 struct kvm_create_guest_memfd {
 	__u64 size;
diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 583341d593c9..a2b7c2f1c49f 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -589,6 +589,11 @@ bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm)
 	return true;
 }
 
+bool __weak kvm_arch_supports_gmem_migration(struct kvm *kvm)
+{
+	return false;
+}
+
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 {
 	static const char *name = "[kvm-gmem]";
@@ -623,11 +628,16 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
 	inode->i_mapping->a_ops = &kvm_gmem_aops;
 	inode->i_mode |= S_IFREG;
 	inode->i_size = size;
-	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 	mapping_set_inaccessible(inode->i_mapping);
-	mapping_set_unmovable(inode->i_mapping);
-	/* Unmovable mappings are supposed to be marked unevictable as well. */
-	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
+	/* guest_memfd mappings should be marked unevictable. */
+	mapping_set_unevictable(inode->i_mapping);
+
+	if (flags & GUEST_MEMFD_FLAG_MIGRATABLE) {
+		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE);
+	} else {
+		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+		mapping_set_unmovable(inode->i_mapping);
+	}
 
 	GMEM_I(inode)->flags = flags;
 

-- 
2.43.0